Method for clustering image areas through LLC based on adaptive codebook

Abstract

The invention relates to a method for clustering image areas through LLC based on an adaptive codebook. Color, texture, Gabor, center of mass and other features are extracted from the segmented super-pixels and then the neighbor areas are clustered through the fused features, the identifiable degree between the multiple neighbor areas is enhanced by the form of a similarity structure diagram, the extremely valuable clues are provided for reducing and even eliminating the noise near the boundary of the foreground in the generated saliency map and the boundary of the foreground is enabled to be clearer; multiple features are used as the basis for calculating the saliency map, and when the color feature cannot be used for effectively extracting the saliency target under the complex scene, multi-feature information is used as the beneficial supplement to effectively enhance the detection result; and as the extended LLC coding scheme, the method that multiple feature descriptors in the original LLC are coded and then fused in the objective function is extended into the method that the multiple feature descriptors are fused firstly and then coded in one step so that the coding process can be simplified and the integrity of the multiple features can be emphasized.

Description

technical field [0001] The invention relates to the fields of pattern recognition technology, information fusion technology, information coding technology and digital image processing technology, and specifically relates to a method for clustering image regions through LLC based on an adaptive codebook. Background technique [0002] Pattern recognition technology refers to the process of processing and analyzing various forms of (numerical, textual and logical) information representing things or phenomena to describe, identify, classify and explain things or phenomena. An essential part of science and artificial intelligence. Pattern recognition in saliency detection refers to the recognition and classification of background and objects in images. A salient target is a person or thing that stands out from the background in an image, and generally contains more interesting and useful information. The main task of salient object detection is to detect and mark the area where...

AI Technical Summary

Problems solved by technology

On the other hand, when the image scene is complex, it is difficult for machine vision to detect the foreground from the cluttered background, resulting in the phenomenon of more noise near the foreground area and even blurred foreground boundaries in the saliency map generated by various advanced algorithms. The difficulty of foreground or object recognition

Images